One meeting that fixes scope, roles, and dates in writing.
A pre-read, a timed sixty-minute agenda, and a recap email, built from your signed scope and the people who will attend.
Kickoff meetings are often a friendly introduction and a slide deck. The cost arrives in week four, when two people remember different scopes and no one is sure who approves the designs. Disagreements are cheap on day one and expensive in week six.
Project Kickoff builds the pre-read, a time-boxed agenda, an explicit in-and-out scope list, roles for doing, approving, and consulting, a dated milestone list with client dependencies flagged, and the working rules for updates and changes. It ends with the recap email that asks the client to reply confirmed.
What it produces.
- →A one-page pre-read with questions for the client
- →A sixty-minute agenda with time and speaker per block
- →A scope in-and-out list and a roles table
- →A recap email to send within 24 hours
- ✦Project managers running the first client meeting
- ✦Agency leads who inherit unclear scopes
- ✦Consultants starting implementations with a client team
- →project-kickoff.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →project-kickoff-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
- →A README inside the zip with install steps for Claude, ChatGPT, and Gemini
What it does with a real question.
We signed a $48,000 website rebuild with a regional credit union, and the kickoff is next Tuesday, March 11. Their side will be the marketing director, an IT lead, and a compliance officer; mine is a project manager, two developers, and a designer. Launch is set for June 20, and I need a kickoff agenda that locks scope, roles, and milestones.
Build the Tuesday agenda around the out list. With a credit union, the risk to June 20 is not design taste. It is compliance review and IT security sign-off arriving late, so the 60 minutes should lean on scope exclusions and dependencies more than introductions. Spend five minutes on the goal, fifteen on what is in and, more importantly, what is explicitly out. Think online banking login integration, member data migration, and any third-party calculators or rate tools. Those are where a rebuild quietly grows past $48,000.
Use ten minutes on roles. Name one decider on their side, almost certainly the marketing director, and give the compliance officer a defined review gate instead of an open veto. Without that, every page can be reopened after design approval. Spend fifteen minutes on dates: ask the compliance officer to commit to a turnaround time per round, and ask the IT lead for DNS, hosting, and security review dates, since those are the two that can move launch. Close with ten minutes on revision rounds and change requests, then a five-minute recap.
Send a one-page pre-read by Sunday, March 9, with three questions: who signs off on legal disclosures, which systems must stay untouched, and what content already exists. Your next move is to draft that pre-read and send it to all three attendees today.
The full Playbook runs the whole procedure and writes the complete deliverable, not this excerpt.
Written by claude-sonnet-5-5 with this Playbook loaded, 2026-10-11. Checked automatically for length and for copied framework text.
No subscription · free updates within v1.x
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Before you buy.
How is this different from just asking Claude directly?
Asked cold, Claude writes a generic kickoff agenda. This is built around the agreements you need at the end of the meeting, makes you write the out-of-scope list, assigns approvals by name, and checks the recap against what was actually discussed.
How is this different from a Tool?
Playbooks are systematically produced to a fixed template and priced accordingly ($12.99). Tools are hand-built, one at a time, and go deeper ($39 to $199). A Playbook gives you a reliable method for routine work; a Tool is for when the judgment matters more than the format.
Will this work with ChatGPT, Gemini, and other LLMs?
Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.
Can I share this with my team?
It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Playbook itself in the hands of a whole team, email hello@authority.md about team licensing.
What if it doesn't work for me?
If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.